Qdrant

Qdrant MCP Connector for Claude

A+

Empower your AI to interact directly with your Qdrant vector database — query clusters, perform similarity searches, and manage collections effortlessly.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Qdrant vector database (Cloud or Self-Hosted) to any AI agent and bring powerful semantic retrieval and database management into your conversation.

What you can do

  • Discover Collections — List all vector collections in your cluster, fetch detailed distance metrics, and monitor total payload points instantly
  • Semantic Vector Search — Perform nearest neighbor similarity searches. Pass a JSON array of floats and retrieve the exact payloads matching your query
  • Data Management — Read specific points by ID or scroll sequentially through giant datasets to debug payloads and embedding quality
  • Mutation Operations — Delete redundant data points safely without building separate admin scripts

How it works

  1. Subscribe to this server
  2. Provide your Qdrant Base URL and API Key
  3. Start querying your embeddings directly from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI & ML Engineers — query embedded spaces directly from your console while building RAG (Retrieval-Augmented Generation) applications
  • Data Scientists — inspect payloads and test distance parameters on live indices without launching Jupyter Notebooks
  • Backend Developers — manage vector cluster configuration and clear bad datasets efficiently
vector-databasesemantic-searchembedding-managementdata-retrievalvector-search

7 tools expose this connector's capabilities to your AI agent.

list_collections

Lists all collections in the Qdrant instance

get_collection

Retrieves detailed information about a specific collection

search

You must provide a JSON array of floats for the query vector. Performs a nearest neighbor vector search in a collection

get_points

Retrieves specific points by their IDs

scroll

Returns points with their payloads. Scrolls through points in a collection, useful for pagination

count

Counts the total number of points in a collection

delete

This action is irreversible. Deletes specific points from a collection

See how to talk to your AI agent using Qdrant.

List the configurations for all collections in my Qdrant instance.

I found 2 collections. 1. `docs-embeddings`: Contains 4,500 points, optimized using Cosine distance, vector size 1536. 2. `image-features`: Contains 120,400 points, optimized using Dot product, vector size 512. Should I inspect `docs-embeddings` further?

Count the total embedded points in the 'docs-embeddings' collection.

The `count` tool indicates there are exactly 14,235 points currently indexed in the `docs-embeddings` collection.

Scroll and show me the IDs and payloads of the first 3 items in the 'users' collection.

Scrolling through 'users', here are the top 3 IDs and payloads: 1. ID: `1f2a3`, Payload: { "role": "admin", "department": "sales" } 2. ID: `7b9c1`, Payload: { "role": "user", "department": "support" } 3. ID: `9d8e4`, Payload: { "role": "user", "department": "sales" }

For **Qdrant Cloud**: Go to the Qdrant Cloud Console, select your cluster to open the Cluster Detail Page. The endpoint will be displayed there (e.g., `xyz.us-east4-0.gcp.cloud.qdrant.io`), and you can generate Database API Keys underneath it (they start with `eyJhb`). For **Self-hosted**: Provide your custom URL and the static custom key you defined in your `config.yaml`.

Related Connectors